Policy & Regulation
New York City Mayor Zohran Mamdani called on residents to resist inevitability narratives around AI and demand protective regulations. Mamdani criticized federal authorities for abdicating responsibility on AI governance. Source: TechCrunch
Frontier & Research
Nscale and Anthropic are reportedly in discussions for an additional $45 billion compute deal, following their August announcement of a similar arrangement. The potential deal underscores significant investment in computational infrastructure to support AI model development and deployment. Source: TechCrunch
Frontier & Research
OpenAI has developed new evaluation methods to improve ChatGPT's performance across low-resource programming languages, including software engineering tasks, SQLite, and COBOL migration. The work addresses capability gaps in languages that have limited training data and real-world usage examples. Source: OpenAI
Policy & Regulation
Hugging Face's chief policy officer Irene Solaiman has stated that AI model benchmarking methods are complicated and still maturing, challenging the notion that evaluations provide neutral and accurate comparisons between AI products. The discussion highlights concerns about the reliability of the evaluation systems that AI labs use to
Policy & Regulation
Microsoft has issued guidance warning that AI agents should be monitored similarly to insider threats, cautioning that frontier models from outside controlled environments cannot be fully trusted. The company recommends enterprises carefully oversee which AI agents their employees deploy and use. Source: TechCrunch
Tools & Products
Amazon has released TorchNeuron, a developer tool designed to enable PyTorch applications to run on non-Nvidia chips, including Amazon's own processors. The move aims to reduce developer dependence on Nvidia's hardware dominance in AI model training and deployment. Source: TechCrunch
AI in Business
Hackers compromised OpenCode's online platform and stole user API keys, enabling unauthorized access to users' AI accounts and service charges. The incident highlights security vulnerabilities in open-source AI coding tools and the limitations of AI models in detecting malicious code patterns. Source: TechCrunch
AI in Business
Tolan, an AI companion app, has raised $30 million in new funding and reports over 250,000 active users. The funding round reflects continued investor interest in consumer-facing AI companion applications. Source: TechCrunch
Policy & Regulation
Personal AI agents that automate online tasks are proliferating rapidly, creating conflicts with website systems designed for human users, forcing platforms to choose between blocking agents or redesigning for them. The internet's future design—optimized for AI agents rather than humans—could fundamentally reshape web experiences, pricing transparency,
Tools & Products
Eugenia Kuyda, founder of Replika, has launched a new startup called Wabi that offers a free personal AI assistant, building on concepts she pitched at TechCrunch Disrupt over 12 years ago. Wabi positions itself as an accessible AI assistant available for download to the general public. Source: TechCrunch
Frontier & Research
Researcher Nick Cammarata published a 26,000-word article claiming that large language models may be more interpretable than previously thought, suggesting that neural networks follow discoverable logical patterns rather than being fundamentally inscrutable. While Cammarata's findings have generated significant excitement in the AI community, prominent researchers including
AI in Business
Tenstorrent raised $1.5 billion in funding, reaching a $6.2 billion valuation while choosing to remain independent despite earlier acquisition interest. The company is positioning itself as a competitor to Nvidia in the open-weight AI chip market. Source: TechCrunch